Plugin
Sfoglia, filtra e installa i plugin di DeepSeek-Harness.
120 plugin trovati
dsh-secret-scrub
jkt-check/dsh-secret-scrub
Guardia di pulizia irreversibile dei segreti: riscrive chiavi di accesso, token bearer e blocchi di chiave privata come segnaposto `[REDACTED:<category>]` prima che raggiungano il log di sessione e il modello.
dsh-plugin-context-manager
luxiwusuobuneng/dsh-plugin-context-manager
Gestore di contesto per DeepSeek Harness: riassume automaticamente ogni turno in record ordinati per priorità, li inietta insieme a note cross-sessione fissate e testo personalizzato in ogni richiesta al modello, e condensa in riassunti, per risparmiare token, intervalli di conversazione reale di qualsiasi dimensione. Persistente e sicuro ai riavvii. NOTA: installazione manuale in più passaggi — copia le tre cartelle del pacchetto in profiles/node_modules e aggiungi le righe fornite di cordis.patch.yml, poi riavvia DSH; non è un'installazione standard con un solo comando.
dsh-at-skill
452926826/dsh-at-skill
Con token @name l'utente può invocare le Skill accessibili, e nel composer della conversazione compaiono i suggerimenti di Skill corrispondenti.
dsh-deepseek-balance-widget
crazy-l118/dsh-deepseek-balance-widget
Widget del saldo API DeepSeek per la barra laterale web di dsh: una pillola di saldo in diretta e ad aggiornamento automatico (saldo / spesa odierna / token odierni) con popover di dettaglio (spesa cumulativa, uso mensile, conteggio richieste). Ogni utente vede solo il proprio saldo; le chiavi sono riso
dsh-stylevault
gptsapp/dsh-stylevault
30 palette di temi open source classiche (Catppuccin, Nord, Tokyo Night, Gruvbox, Solarized, ecc.) mappate sui token ufficiali del ThemeService per DeepSeek Harness, con un pannello Style Settings per modifiche live di colori/font/raggio ed esportazione/importazione JSON per condividere pacchetti di configurazione.
dsh-wildmon
swaylq/dsh-wildmon
Catch-em-all stile Pokemon: il tuo lavoro vero è l'erba alta — turni, chiamate agli strumenti ed errori generano incontri selvatici; lancia sfere, riempi un dex da 28 slot, schiera una squadra di sei. Zero token, invisibile al modello.
dsh-cache-miss
wefio/dsh-cache-miss
Avviso giallo su una riga per un cache miss del prompt dopo la ricostruzione della cache; mostra i token di input non memorizzati nuovamente fatturati, i token trovati nella cache e il TTFT.
dsh-skin20260814
manuspurs/dsh-skin20260814
Versione avanzata di dsh-skin: offre cambio skin e sfondo personalizzato per DeepSeek Harness. Rispetto alla versione originale corregge due problemi — ① upload di immagini grandi/formati speciali senza risposta (ora si usa createImageBitmap per la decodifica diretta, con indicatori di elaborazione ed errore); ② overrideTokens che al cambio tema innescava theme/change causando un overflow dello stack per ricorsione infinita (aggiunta una guardia skin/chiaro-scuro per interrompere il ciclo). L'archiviazione degli sfondi è passata dalla compressione in localStorage al salvataggio diretto del file originale in IndexedDB, con visualizzazione a piena qualità, zero compressione, e migrazione automatica dei dati precedenti
dsh-plugins
youssefsiam38/dsh-plugins
Side-by-side model comparison for the DeepSeek Harness Web UI: send one prompt to 2–4 models in sibling sessions forked from the current one, watch the answers stream in columns (tabs on phones) with latency, time to first token, tokens, and cost, then co
dsh-orca-glass
huzhengbang2007/dsh-orca-glass
DSH Web plugin that injects an SVG (feTurbulence + feDisplacementMap) refraction filter and applies it through backdrop-filter to panels, bubbles and the input card, and bundles the orca-scene skin with theme tokens plus light and dark backgrounds.
dsh-usage-heatmap
zeng6125-rgb/dsh-usage-heatmap
Token usage dashboard in the DSH settings page: nine metric cards (total, today, yesterday, peak day, longest session, active-day streak, active days, sessions, subagent tokens), a GitHub-style daily/weekly/cumulative heatmap, and an activity insight list, aggregated locally from session logs and projection caches, keeping token history after a session is deleted.
tool-guardian
luminarisoftwares/tool-guardian
Fronts stdio MCP servers with three router tools (list_capabilities, describe_tool, call_tool) so schemas load on demand instead of riding every request; shapes every tool result through a deterministic output ladder that archives the original first (retrieve_spill reads it back); prices tool groups in tokens and can hide built-in groups per agent. Bridges to a standard-library Python router, so Python 3.9+ is required.
dsh-compact-agents
zhuto666/dsh-compact-agents
Model-callable compact_agents tool that force-compacts context in every live session (main session, ordinary sub-agents and AgentTeams members alike), queues busy targets and compacts them when the turn ends, reports the shadowed node count and estimated tokens per target, and ships a browser form for the trigger ratio, retained ratio, controlled-phase output budget, auto-continue budget and an end-of-turn pre-compaction ratio that compacts near the trigger line once a turn ends, so a reply no longer opens with a wait for the summarizer.
dsh-context-compression-improved
drscrewdriver/dsh-context-compression-improved
Same-origin in mechanism with the two loudest lines in context compression. The code-skeleton gate follows the skeletonization approach of Headroom (Apache-2.0), whose published headline is 20% fewer tokens for coding agents and 60–95% fewer tokens for JSON, same answers. The estimator channel follows TokenPilot (arXiv:2606.17016), which reports up to 60% lower cost for long-session agents. Both figures are theirs, quoted as-is; this plugin ships no benchmark of its own and claims no reduction of its own. What it adds for DeepSeek Harness: choose a compression profile, set the Auto Compact trigger level and toggle code-skeleton compression from one settings section, with exact DeepSeek V4 tokenizer measurement, same-revision count verification, and fail-open behaviour that keeps the original tool results on unsupported models.
dsh-tps-meter
looking321-rt/dsh-tps-meter
DeepSeek Harness Web 悬浮窗:实时显示会话输出吞吐(tok/s)、本步/累计 token 与首 token 延迟,支持实时/均速双口径与多会话切换。
dsh-kaze-tachinu-theme
suuuuunamei/dsh-kaze-tachinu-theme
Kaze Tachinu (The Wind Rises) skin for the DSH Web GUI: a full-screen film wallpaper behind glassmorphism surfaces, sky-blue interaction tokens, redrawn vector logos for the sidebar and home hero, a restyled composer card with themed placeholder text, and a bottom fade on the message list.
dsh-git-credentials
revive/dsh-git-credentials
Out-of-tree dsh plugin: GitLab, GitHub, Gitee, Gitea, and Bitbucket tokens stay out of the model context, stored encrypted (AES-256-GCM) in a plugin-owned file; the model calls forge API tools on demand, and the web settings page manages sites and tokens.
dsh-turnbar
rex178178/dsh-turnbar
Video-style turn navigation for the Web UI: full-map progress bar with hover preview cards (tools/files/tokens), drag scrub, ⌘K in-conversation search, ⌘↑/⌘↓ stepping, Esc-return. Event-log powered — works beyond the loaded window. Dual-half plugin on the official composer.dock slot.
dsh-wsl-clock
173787247/dsh-wsl-clock
Detects WSL2 clock skew versus Windows that can break TLS and tokens.
dsh-plugin-gemini-theme
dingyi580/dsh-plugin-gemini-theme
Gemini-styled skin restyling the conversation ground, sidebar rows, hero greeting and composer through one stylesheet over the --dsw-* tokens, with light and dark both covered.
dsh-token-speed
gbeta/dsh-token-speed
Draggable ring gauge showing live model output speed (tok/s) with an expandable per-step detail panel (exact speed, TTFT, cache-hit rate, cache read/write, reasoning and input tokens, model, cumulative tokens).
dsh-continue-on-limit
qwert702/dsh-continue-on-limit
Auto-continue for the dsh web GUI: when a local model hits its output-token cap and the max-tokens notice appears, the plugin automatically queues a short continue message so the reply keeps flowing — dual-source truncation detection, loop protection, and no UI.
dsh-usage
huasecc/dsh-usage
DeepSeek account-wide usage & balance panel from the official platform API (api/v0/usage/by_api_key): cache hit/miss & output tokens, cost, 24h–90d ranges, persistent platform token, and a model-visible `deepseek_usage_query` tool.
dsh-always-status-bar
bobnemimimmi/dsh-always-status-bar
Keeps the native per-message status line always visible without hovering — date and time on every message, run duration, TTFT, and tokens per second on assistant messages.